Tomato Leaf Disease Detection

Tomato leaf diseases seriously threaten agricultural productivity, making early and precise detection techniques essential. This study uses Convolutional Neural Networks (CNNs) enhanced by Efficient Neural Architecture Search (ENAS) to detect tomato leaf illnesses using a deep learning-based method. To improve classification accuracy and lower computing complexity, the study integrates an automated pipeline for data preparation, augmentation, and model training. According to experimental findings, the ENAS-optimized CNN model performs more accurately and efficiently than traditional CNN designs. Future research will use edge computing and multi-modal data analysis to detect diseases in agricultural settings in real time.